Blending Artificial Intelligence and Machine Learning with the Internet of Things: Emerging Trends, Issues and Challenges

Dear Colleagues,

The Internet of Things (IoT) continues to revolutionize the world. However, gathering, processing, and analyzing the data is difficult due to the volume of data flowing from billions of connected IoT devices. Artificial intelligence can play a vital role here, as it can extract insights from data. Machine learning can detect patterns and anomalies in data obtained from IoT devices. As a result, networks and devices can learn from previous decisions, predict future activity, and continuously enhance their performance and decision-making capabilities.

This Special Issue aims to bring together researchers and scientists to present the latest experiences, findings, and developments regarding integrating artificial intelligence and machine learning with the Internet of Things. The topics of this Special Issue include, but are not limited to, the following:

• Artificial intelligence and IoT;
• Machine learning and IoT;
• IoT recent trends;
• IoT applications and services;
• IoT networks;
• IoT architectures;
• IoT prototypes, testbeds, and case studies.

Prof. Dr. Vasco N. G. J. Soares
Prof. Dr. João M. L. P. Caldeira
Dr. Bruno Bogaz Zarpelão
Dr. Jaime Galán-Jiménez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Internet of Things
• artificial intelligence
• machine learning
• trends
• issues
• challenges

Title: Uncovering the Unexpected: A Review of Anomaly Detection Techniques in IoT using Machine Learning
Authors: Rameez Asif
Affiliation: --
Abstract: With the rapid proliferation of the Internet of Things (IoT), the amount of data generated by these devices has grown exponentially, making it increasingly challenging to identify anomalies and potential security threats. In this review paper, we provide an overview of various anomaly detection techniques for IoT using machine learning algorithms. We first discuss the different types of anomalies that can occur in IoT systems and their potential impact. We then review the state-of-the-art machine learning algorithms used for anomaly detection in IoT, including unsupervised and supervised learning methods, deep learning techniques, and ensemble methods. We also examine the challenges and limitations of using machine learning for anomaly detection in IoT, including data quality issues, privacy concerns, and the need for interpretability. Our findings suggest that machine learning-based anomaly detection can be an effective tool for enhancing security and trust in IoT systems, but requires careful consideration of the data characteristics and the specific application context.

Title: Energy efficient lifetime enhancement for WSN using network trust and swarm intelligence optimization
Authors: Sung Won Kim
Affiliation: Department of Information and Communication Engineering, Yeungnam University, Gyeungsan, Gyeungbuk 38541, Korea
Abstract: For specialized telecommunication applications, recent developments in technology and manufacturing have made it possible to develop compact, powerful, energy-efficient, cost-effective sensor nodes which are “smart” enough to be capable of adaptability, self-awareness, and self-organization. Sensor network technologies improve social advancement and life quality while having little to no negative impact on the environment or natural resources of the planet are examined in sensor networks for sustainable development. Wireless sensor networks (WSNs) are advantageous in a wide range of applications, including military, healthcare, traffic monitoring, and remote sensing of images. Different levels of security are needed for these critical applications and it becomes difficult to use conventional algorithms due to the limitations of sensor networks. Sensor networks are also thought of as the foundation of the IoTs and smart cities, where security has emerged as one of the biggest issues with IoT and smart city applications. The WSN covers complex issues like energy consumption, an effective method for choosing cluster heads, a routing algorithm, network strength, packet loss, energy loss, and other issues. With the recent introduction of WSNs, it has become more difficult to supply trustworthy and reliable data because of the distinctive properties and limitations of nodes. Through the insertion of fake and malicious data as well as the launch of internal attacks, hostile nodes can easily compromise the integrity of the network. Using trust-based security to detect rogue nodes provides an efficient and portable defence. To increase dependability (cooperation) among sensor nodes in wireless sensor networks, trust evaluation models are a crucial security enhancement tool. To meet the security needs of WSNs, this study suggests the novel trust algorithm DFA U-Trust.

Title: Digital Twins for Smart Manufacturing: Opportunities and Challenges
Authors: Nader Mohamed and Jameela Al-Jaroodi
Affiliation: --
Abstract: Smart manufacturing represents the modern digital industrial innovations. This vision is realized through utilizing the advances in technologies like the Internet of Things (IoT), Artificial Intelligence (AI) and Machine Learning (ML) to enable various advanced smart applications. The smart manufacturing/industrial applications enable fast demand-based production and better optimization for the supply chain, in addition to reliable, efficient, and cost-effective production. One key technology that has significant potential to improve the capabilities and outcomes of smart manufacturing is digital twins. This paper investigates the opportunities and challenges of utilizing digital twins for smart manufacturing. It also discusses the current research trends in the field and future prospects.